Skip to content

Brand-System/brandsystem-mcp

v0.16.1 Bugfix

This release fixes issues for SREs watching stability and regressions.

Published 7d MCP Developer Tools
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai-agents brand-governance brand-guidelines brand-identity brand-voice claude
+5 more
codex cursor design-tokens mcp model-context-protocol

Summary

AI summary

Fixed MCP error handling to correctly mark failures and updated brand_context paths with accurate documentation.

Changes in this release

Bugfix Medium

Fenced errors now set isError: true in MCP envelope

Fenced errors now set isError: true in MCP envelope

Source: llm_adapter@2026-07-20

Confidence: medium

 —
Bugfix Medium

brand_context instructions reference correct data paths for next_steps and tool description

brand_context instructions reference correct data paths for next_steps and tool description

Source: llm_adapter@2026-07-20

Confidence: medium

 —
Bugfix Medium

A/B receipt‑arm documentation updated to reflect experiment_arm stamping and dirty‑diff hash

A/B receipt‑arm documentation updated to reflect experiment_arm stamping and dirty‑diff hash

Source: llm_adapter@2026-07-20

Confidence: medium

 —
Full changelog

Three findings from the Codex 0.16.0 review, all conceded:

Fixed

  • Fenced errors keep MCP error semantics: the #45 error fence returned the structured envelope without isError: true, so generic MCP clients could classify a failed execution as success. Now returns isError: true with the same fenced envelope.
  • brand_context instructions point at real paths: next_steps and the tool description referenced data.context / data.output_contract; buildResponse spreads data at the top level. Corrected, with client-level path assertions.
  • A/B receipt-arm documentation corrected: clean/dirty tree stamps do NOT distinguish experiment arms (receipts accumulate as untracked files). RESULTS.md prose corrected, scores unchanged; receipts now stamp experiment_arm (EVAL_ARM env) + a dirty-diff hash.

1,004 tests.

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track Brand-System/brandsystem-mcp

Get notified when new releases ship.

Sign up free

About Brand-System/brandsystem-mcp

Make your brand machine-readable. Extract brand identity (colors, fonts, logo, voice, visual rules) from any website via static CSS + rendered-page extraction, compile into DTCG tokens, brand runtime contracts, and interaction policies. 34 tools across 4 progressive sessions. Subscribable `brand://runtime` and `brand://policy` MCP resources. Content compliance scoring (0-100), pass/fail gate, and HTML/CSS preflight. Brandcode Studio connector for hosted brand sync.

All releases →

Related context

Beta — feedback welcome: [email protected]